About me

I am currently a Ph.D. student in the Paul G. Allen School of Computer Science & Engineering at the University of Washington. I am very fortunate to be advised by Professor J. Nathan Kutz on sparse regression and deep learning methods for equation discovery. My research interests are in deep learning, statistical learning theory, and bayesian methods. I love to develop generalizable and interpretable learning frameworks that not only address practical challenges but also contribute to our understanding of the natural world. Ultimately, I hope to employ these methods in real life and solve complex scientific problems.

Publication

• Bayesian autoencoders for data-driven discovery of coordinates, governing equations and fundamental constants.
  Mars L. Gao, J. Nathan Kutz. Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences. link

• Convergence of uncertainty estimates in Ensemble and Bayesian sparse model discovery.
  Mars L. Gao, Urban Fasel, Steven L. Brunton, J. Nathan Kutz. Preprint. link

• Bayesian data-driven discovery of partial differential equations with variable coefficients.
  Aoxue Chen*, Yifan Du*, Mars L. Gao*, Guang Lin. [Submitted].

• On Optimal Early Stopping: Over-informative versus Under-informative Parametrization.
  Ruoqi Shen, Mars L. Gao, Yi-An Ma. [Submitted]. paper link

• DeepGLEAM: A hybrid mechanistic and deep learning model for COVID-19 forecasting.
  Dongxia Wu, Mars L. Gao, Xinyue Xiong, Matteo Chinazzi, Alessandro Vespignani, Yi-An Ma, Rose Yu. preprint (2021). arXiv*
  

• Deformation Robust Roto-Scale-Translation Equivariant CNNs.
  Mars L. Gao, Guang Lin, Wei Zhu. Transactions on Machine Learning Research (TMLR). link

• RotEqNet: Rotation-Equivariant Network for Fluid Systems with Symmetric High-Order Tensors.
  Mars L. Gao, Yifan Du, Hongshan Li, Guang Lin. Journal of Computational Physics. arXiv
  

• Quantifying Uncertainty in Deep Spatiotemporal Forecasting
  Dongxia Wu, Mars L. Gao, Xinyue Xiong, Matteo Chinazzi, Alessandro Vespignani, Yi-An Ma, Rose Yu. SIGKDD (2021). arXiv and Code
  

• Non-convex Learning via Replica Exchange Stochastic Gradient MCMC
  Wei Deng, Mars L. Gao*, Qi Feng*, Faming Liang, Guang Lin. ICML 2020. arXiv and Code*
  

• Evaluation of probabilistic forecasts of COVID-19 mortality in the US
  Estee Y Cramer, Evan L Ray, Velma K Lopez, Johannes Bracher, Andrea Brennen, et al. PNAS. medRxiv
  

• H-DrunkWalk: Collaborative and Adaptive Navigation for Heterogeneous MAV swarm
  Xinlei Chen, Carlos Ruiz, Sihan Zeng, Mars L. Gao, Aveek Purohit, Stefano Carpin, Pei Zhang, et al. Transactions on Sensor Networks. ACM, 2020. ACM*
  

• Rotation-equivariant convolutional neural network ensembles in image processing
  Mars L. Gao, Hongshan Li, Zheying Lu, Guang Lin. Ubicomp CPD Workshop. ACM, 2019. ACM and code
  

Study notes

• High Dimensional Probability and Statistical Learning Notes

• Advanced Theory of Statistical Inference Chap.1 Chap.2 Chap.3 Chap.4 Chap.5 Chap.6

• Log-Sobolev Inequality short notes

• Optimal Transport

• Bayesian Statistics

• Measure theory notes for probability

  Services

• Reviewers: Nature Communications, Journal of Machine Learning Research, Uncertainty in Artificial Intelligence (UAI).

Contact

Email: marsgao AT uw DOT edu